Sensorless control of AC motor drives,which takes the advantages of cost saving,higher reliability,and less hardware,has been developed for several decades.Among the existing speed sensorless control methods,nonlinear...Sensorless control of AC motor drives,which takes the advantages of cost saving,higher reliability,and less hardware,has been developed for several decades.Among the existing speed sensorless control methods,nonlinear Kalman filter-based one has attached widespread attention due to its superb estimation accuracy and inherent resistibility to noise.However,the determination of noise covariance matrix and robustness of model uncertainties are still open issues in practice.A great number of studies try to solve these problems in resent years.This paper reviews the application of extended Kalman filter(EKF),unscented Kalman filter(UKF),and cubature Kalman filter(CKF)in speed sensorless control for AC motor drives.As an iterative algorithm,EKF has advantages in processor implementation.However,EKF suffers from the linearization error and model uncertainties when applying to sensorless control system.This paper presents the predominant improvements of EKF which is also applicative in UKF and CKF mostly.展开更多
A power tool for the analysis of quasi-Newton methods has been proposed by Byrd and Nocedal ([1], 1989). The purpose of this paper is to make a study to the basic property (BP) given in [1]. As a result of the BP, a s...A power tool for the analysis of quasi-Newton methods has been proposed by Byrd and Nocedal ([1], 1989). The purpose of this paper is to make a study to the basic property (BP) given in [1]. As a result of the BP, a sufficient condition of global convergence for a class of quasi-Newton methods for solving unconstrained minimization problems without convexity assumption is given. A modified BFGS formula is designed to match the requirements of the sufficient condition. The numerical results show that the proposed method is very encouraging.展开更多
基金This work was supported in part by National Natural Science Foundation of China(51677150)in part by State Key Laboratory of Large Electric Drive System and Equipment Technology(SKLLDJ012016006)+1 种基金in part by Key Research and Development Project of ShaanXi Province(2019GY-060)in part by Key Laboratory of Industrial Automation in ShaanXi Province(SLGPT2019KF01-12)。
文摘Sensorless control of AC motor drives,which takes the advantages of cost saving,higher reliability,and less hardware,has been developed for several decades.Among the existing speed sensorless control methods,nonlinear Kalman filter-based one has attached widespread attention due to its superb estimation accuracy and inherent resistibility to noise.However,the determination of noise covariance matrix and robustness of model uncertainties are still open issues in practice.A great number of studies try to solve these problems in resent years.This paper reviews the application of extended Kalman filter(EKF),unscented Kalman filter(UKF),and cubature Kalman filter(CKF)in speed sensorless control for AC motor drives.As an iterative algorithm,EKF has advantages in processor implementation.However,EKF suffers from the linearization error and model uncertainties when applying to sensorless control system.This paper presents the predominant improvements of EKF which is also applicative in UKF and CKF mostly.
文摘A power tool for the analysis of quasi-Newton methods has been proposed by Byrd and Nocedal ([1], 1989). The purpose of this paper is to make a study to the basic property (BP) given in [1]. As a result of the BP, a sufficient condition of global convergence for a class of quasi-Newton methods for solving unconstrained minimization problems without convexity assumption is given. A modified BFGS formula is designed to match the requirements of the sufficient condition. The numerical results show that the proposed method is very encouraging.
